© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51483
    Prev
    Next
    INDEX
    Explanations

    echo / Echo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agna
    -0.09
    agement
    -0.09
    mente
    -0.09
    è¡©
    -0.09
    ucha
    -0.08
    olas
    -0.08
    ÑĪе
    -0.08
    طا
    -0.08
    aven
    -0.08
    ç¢į
    -0.08
    POSITIVE LOGITS
    ../../../
    0.11
    äºĨåĩł
    0.10
    stry
    0.10
    obot
    0.10
    ÑģÑĤанов
    0.10
    arf
    0.09
    apse
    0.09
    uated
    0.09
    alis
    0.09
    gable
    0.09
    Activations Density 0.025%

    No Known Activations